MADHAV JAYESH VYAS
(***) *** - **** Atlanta, GA ad2hid@r.postjobfree.com www.linkedin.com/in/madhav-vyas-0a6203b9
EDUCATION
New York University Tandon School of Engineering, New York, NY May 2017
Master of Science in Industrial Engineering
Gujarat Technological University, Ahmedabad, India May 2015
Bachelor of Engineering in Mechanical Engineering
Udacity – Data Scientist Nanodegree July 2019
Related coursework: Machine Learning and Regression Analysis, Supply Chain Engineering, Supply Chain Competitiveness, Operations Research, Project Management, Operations Management, Quality Control & Improvement, Product Design &Value Engineering, Production Science
SKILLS
Machine Learning: Regression Analysis, Artificial Neural Network, Decision Tree Regression, Random Forest and Logistic Regression, HoltWinters and ARIMA Forecast Modelling, Clustering and Confusion Matrix
Python: Pandas, Numpy, Scikit Learn, Matplotlib, Seaborn, Tensorflow, Pytorch, and Keras
MS Excel: Vlookup & Index/Match, Pivot and Power Pivot Table, Macros, Solver, Conditional Formatting, Data Management, Statistical Analysis ToolPak
SQL: Joins, Stored Procedures, Window Functions, CTEs, Date-Time Functions, PIVOT, and other data wrangling functions
SAP IBP, SAP S/4HANA, SAP Analytics Cloud, Alteryx
EXPERIENCE
Georgia Pacific LLC, Atlanta, GA
Senior Demand Planner & Demand Data Specialist September 2021-Present
In the SAP IBP Demand module, create and optimize statistical forecasting models such as Auto Exponential Smoothing, Crostons, and Gradient Boosting Algorithms which resulted in forecast error improvement by 15% annually
Develop a Forecast Automation approach in SAP IBP using Time Series Analysis to optimize statistical forecast model application on different products with various demand patterns to consider level, trend, and seasonality to help reduce overstock and stock-out situation
Lead value segmentation methodology using Alteryx workflow and SAP IBP to optimize the S&OP process by calculating forecast value add across different customers and products for supply chain cost optimization
Build ETL pipelines in Alteryx using EHANA/SQL queries and automate reports for supply chain leadership stakeholders
Manage master data creation and maintenance in SAP IBP for sustainable demand and supply planning activities across the organization
Perform anomaly detection using Python to find the outliers in time series and remove them to make the base forecast more accurate
Rogue Fitness, Columbus, OH
Senior Demand Planning & Data Analyst May 2020-August 2021
Managed and analyzed monthly $80 million worth of fluctuating demand during COVID-19 and optimized the supply chain pipeline across the globe from raw material suppliers to customers
Used SQL window functions, CTEs, and stored procedures to create reports and use them to manage KPI dashboards and purchasing scorecards
Performed Recency, Frequency, and monetary (RFM) segmentation in Python on customers to identify which products are core competencies and which products the business needs to invest more to achieve sales targets
Demand Analyst July 2017 – April 2020
Created an ARIMA, Holt-Winters, and ETS statistical forecasting model using R programming and MS Excel for more than 6,000 SKUs
Built and implemented a model that would highlight the products that underperformed/overperformed against the expected sales considering factors such as demand variability, daily forecast, large orders, continuous up/downtrend, time of the year, and type of the product
Built statistical safety stock model for constant lead time and varying demand of the products to optimize the service level
Michael Kors, Supply Chain Analyst Intern, New York, NY May 2016-August 2016
Tracked and reported all inbound products to California distribution center(DC), created monthly floor-set tracking for the planning team
Analyzed/Reported the number of units that met or missed the Service Level Agreement in transportation from the distribution center to company stores
ACADEMIC PROJECTS
Supervised Learning Algorithm Prediction Model at Udacity October 2018 – November 2018
Implemented Decision Tree Classifier, Support Vector Machines, and Adaptive Boosting algorithms to accurately predict individuals' income using data collected from the 1994 U.S. Census
Used sci-kit-learn’s min-max scaler for the data normalization and pandas for the one-hot encoding of the raw data
Based on the accuracy, precision, and recall parameters of models, implemented Adaptive Boosting model which had 89% prediction accuracy